Tuberculosis (TB) is the leading cause of preventable death in HIV-positive patients, and yet often remains undiagnosed and untreated. Chest x-ray is often used to assist in diagnosis, yet this presents additional challenges due to atypical radiographic presentation and radiologist shortages in regions where co-infection is most common. We developed a deep learning algorithm to diagnose TB using clinical information and chest x-ray images from 677 HIV-positive patients with suspected TB from two hospitals in South Africa. We then sought to determine whether the algorithm could assist clinicians in the diagnosis of TB in HIV-positive patients as a web-based diagnostic assistant. Use of the algorithm resulted in a modest but statistically significant improvement in clinician accuracy (p = 0.002), increasing the mean clinician accuracy from 0.60 (95% CI 0.57, 0.63) without assistance to 0.65 (95% CI 0.60, 0.70) with assistance. However, the accuracy of assisted clinicians was significantly lower (p < 0.001) than that of the stand-alone algorithm, which had an accuracy of 0.79 (95% CI 0.77, 0.82) on the same unseen test cases. These results suggest that deep learning assistance may improve clinician accuracy in TB diagnosis using chest x-rays, which would be valuable in settings with a high burden of HIV/TB co-infection. Moreover, the high accuracy of the stand-alone algorithm suggests a potential value particularly in settings with a scarcity of radiological expertise.

OBJECTIVEPreoperative depression has been linked to a variety of adverse outcomes following lumbar fusion, including increased pain, disability, and 30-day readmission rates. The goal of the present study was to determine whether preoperative depression is associated with increased narcotic use following lumbar fusion. Moreover, the authors examined the association between preoperative depression and a variety of secondary quality indicator and economic outcomes, including complications, 30-day readmissions, revision surgeries, likelihood of discharge home, and 1- and 2-year costs.METHODSA retrospective analysis was conducted using a national longitudinal administrative database (MarketScan) containing diagnostic and reimbursement data on patients with a variety of private insurance providers and Medicare for the period from 2007 to 2014. Multivariable logistic and negative binomial regressions were performed to assess the relationship between preoperative depression and the primary postoperative opioid use outcomes while controlling for demographic, comorbidity, and preoperative prescription drug–use variables. Logistic and log-linear regressions were also used to evaluate the association between depression and the secondary outcomes of complications, 30-day readmissions, revisions, likelihood of discharge home, and 1- and 2-year costs.RESULTSThe authors identified 60,597 patients who had undergone lumbar fusion and met the study inclusion criteria, 4985 of whom also had a preoperative diagnosis of depression and 21,905 of whom had a diagnosis of spondylolisthesis at the time of surgery. A preoperative depression diagnosis was associated with increased cumulative opioid use (β = 0.25, p < 0.001), an increased risk of chronic use (OR 1.28, 95% CI 1.17–1.40), and a decreased probability of opioid cessation (OR 0.96, 95% CI 0.95–0.98) following lumbar fusion. In terms of secondary outcomes, preoperative depression was also associated with a slightly increased risk of complications (OR 1.14, 95% CI 1.03–1.25), revision fusions (OR 1.15, 95% CI 1.05–1.26), and 30-day readmissions (OR 1.19, 95% CI 1.04–1.36), although it was not significantly associated with the probability of discharge to home (OR 0.92, 95% CI 0.84–1.01). Preoperative depression also resulted in increased costs at 1 (β = 0.06, p < 0.001) and 2 (β = 0.09, p < 0.001) years postoperatively.CONCLUSIONSAlthough these findings must be interpreted in the context of the limitations inherent to retrospective studies utilizing administrative data, they provide additional evidence for the link between a preoperative diagnosis of depression and adverse outcomes, particularly increased opioid use, following lumbar fusion.

Obsessive–compulsive disorder (OCD), like other illnesses with prominent anxiety, may involve abnormal fear regulation and consolidation of safety memories. Impaired fear extinction memory (extinction recall, ER) has been shown in individuals with current symptoms of OCD [1]. However, contrary to expectations, the only previous study investigating this phenomenon showed a positive correlation between extinction recall abilities and OCD symptomology (i.e., as OCD symptoms worsened, extinction memory improved). The purpose of the current study was to determine if patients with a lifetime diagnosis of OCD (not necessarily currently symptomatic) also demonstrate impairments in extinction memory, and the relationship between OCD symptomology and extinction memory in this type of sample. In addition, we also examined fear renewal, which has never been investigated in an OCD sample. We enrolled 37 patients with OCD, the majority of whom were on serotonin reuptake inhibitors, and 18 healthy control participants in a 2-day paradigm assessing fear conditioning and extinction (Day 1) and extinction retention and renewal (Day 2). Skin conductance responses (SCRs) were the dependent measure. Results, as in the prior study, indicated that the only between-group difference was impaired ER in OCD patients relative to controls. Contrary to our prediction, OCD symptom severity was not correlated with the magnitude of extinction recall. There were no differences in fear renewal between OCD patients and controls.

Schizophrenia is a complex genetic disorder. Gene set-based analytic (GSA) methods have been widely applied for exploratory analyses of large, high-throughput datasets, but less commonly employed for biological hypothesis testing. Our primary hypothesis is that variation in ion channel genes contribute to the genetic susceptibility to schizophrenia. We applied Exploratory Visual Analysis (EVA), one GSA application, to analyze European-American (EA) and African-American (AA) schizophrenia genome-wide association study datasets for statistical enrichment of ion channel gene sets, comparing GSA results derived under three SNP-to-gene mapping strategies: (1) GENIC; (2) 500-Kb; (3) 2.5-Mb and three complimentary SNP-to-gene statistical reduction methods: (1) minimum p value (pMIN); (2) a novel method, proportion of SNPs per Gene with p-values below a pre-defined α-threshold (PROP); and (3) the truncated product method (TPM). In the EA analyses, ion channel gene set(s) were enriched under all mapping and statistical approaches. In the AA analysis, ion channel gene set(s) were significantly enriched under pMIN for all mapping strategies and under PROP for broader mapping strategies. Less extensive enrichment in the AA sample may reflect true ethnic differences in susceptibility, sampling or case ascertainment differences, or higher dimensionality relative to sample size of the AA data. More consistent findings under broader mapping strategies may reflect enhanced power due to increased SNP inclusion, enhanced capture of effects over extended haplotypes or significant contributions from regulatory regions. While extensive pMIN findings may reflect gene size bias, the extent and significance of PROP and TPM findings suggest that common variation at ion channel genes may capture some of the heritability of schizophrenia.